01. ExplorationBench: Measuring AI Systems' Exploration in Verifiable Alien Worlds

85% worth reading · novelty 2.0/3 · benchmark/eval · cs.AI

02. Who Holds the Pen? Let Specifications, Not Agents, Sign Off

85% worth reading · novelty 2.0/3 · new method · cs.MA

03. Coding Agents for Generalized Task and Motion Planning Problems

84% worth reading · novelty 1.9/3 · benchmark/eval · cs.AI

04. LLM Agents Can Easily Tamper With Their Own Traces

85% worth reading · novelty 1.8/3 · benchmark/eval · cs.AI

05. JevOut: Natural Context Can Flip Decision Models

87% worth reading · novelty 1.6/3 · benchmark/eval · cs.CL

06. Agentic Detection of Online Conspiracies

84% worth reading · novelty 1.8/3 · new method · cs.CL

07. Instrumental Monitor Evasion Emerges Under Ordinary Task Pressure

85% worth reading · novelty 1.7/3 · benchmark/eval · cs.AI

08. RAPID: Robot Agentic Programming from Demonstrations

82% worth reading · novelty 1.9/3 · new method · cs.AI

09. Codetta: High-Capacity, Keyless, and Undetectable Multi-Agent Collusion

80% worth reading · novelty 2.0/3 · new method · cs.MA

10. Progressive Skill Discovery as Access Control for Tool-Using LLM Agents: Structural Governance through Role-Scoped Capability Delivery

81% worth reading · novelty 1.8/3 · new method · cs.MA

11. Screen Before You Serve: Simulation for Production Customer Experience AI Agents at 140M Scale

85% worth reading · novelty 1.5/3 · applied system · cs.CL

12. Augur: A Synthetic Decision Lab for Rehearsing Reactions to Product and Policy Changes

78% worth reading · novelty 1.9/3 · benchmark/eval · cs.MA

13. Multimodal Thinking with Renderable Programs

78% worth reading · novelty 1.9/3 · new method · cs.CL

14. AlphaDiverse: Post-Training Local Quantitative Research Agents for Diverse Exploration in Alpha Factor Mining

80% worth reading · novelty 1.6/3 · new method · cs.MA

15. What, When, and How: Audio Description as Constrained Global Optimization

76% worth reading · novelty 1.9/3 · new method · cs.CL

16. GRASP: Generating, Revising, and Assessing for Strategic Planning with Agentic AI

79% worth reading · novelty 1.5/3 · new method · cs.CL

17. REAT: A Reflective Experience-Augmented Tutoring Framework for Multi-turn Mathematical Instruction

76% worth reading · novelty 1.6/3 · new method · cs.MA

18. ARGUS: Role-Aware Event Knowledge Graphs for U.S. Employment-Discrimination Complaints

79% worth reading · novelty 1.4/3 · applied system · cs.CL

19. SAGE: Mitigating Long-Horizon Reasoning Biases via Topological Guidance

66% worth reading · novelty 2.0/3 · new method · cs.AI

20. To Trust or Not to Trust: Retrieval-Augmented Fact Checking in Speech

65% worth reading · novelty 1.6/3 · benchmark/eval · cs.AI